A Comprehensive Review of Optimizing Electric Vehicle Charging with Parallel Convolutional Neural Network: Coordinating Smart Grids and Intelligent Transportation Systems

Abstract

The rapid growth of electric vehicles (EVs) has introduced new challenges in energy management, particularly in coordinating charging infrastructure with smart grids and intelligent transportation systems. Efficient EV charging requires real-time decision-making, load balancing, and integration of renewable energy sources. IoT-enabled smart grid architectures have emerged as a key enabler for managing EV charging by providing continuous monitoring, communication, and control across distributed energy systems. Deep learning techniques, especially Convolutional Neural Networks, have shown significant potential in optimizing EV charging by learning complex patterns in energy consumption and traffic flow data. Parallel convolutional neural networks further enhance performance by enabling simultaneous feature extraction from multiple data sources, improving prediction accuracy and system responsiveness. These models support real-time optimization of charging schedules and load distribution. Optimization techniques such as reinforcement learning and multi-objective optimization are widely used to coordinate EV charging with grid operations and transportation systems. These methods address challenges such as peak load management, charging station allocation, and energy efficiency. Additionally, the integration of EVs into smart grids enables bidirectional energy flow, supporting vehicle-to-grid services and improving grid stability. Despite these advancements, challenges such as scalability, computational complexity, and real-time implementation persist. This review focuses on developments in recent years, highlighting key techniques, architectures, and challenges. The integration of deep learning, IoT, and optimization approaches is expected to play a critical role in future intelligent energy and transportation systems.